Loading...
Please wait, while we are loading the content...
Similar Documents
Identifying scalar behavior in CUDA kernels (2011)
| Content Provider | CiteSeerX |
|---|---|
| Author | Collange, Sylvain |
| Abstract | We propose a compiler analysis pass for programs expressed in the Single Program, Multiple Data (SPMD) programming model. It identifies statically several kinds of regular patterns that can occur between adjacent threads, including common computations, memory accesses at consecutive locations or at the same location and uniform control flow. This knowledge can be exploited by SPMD compilers targeting SIMD architectures. We present a compiler pass developed within the Ocelot framework that performs this analysis on NVIDIA CUDA programs at the PTX intermediate language level. Results are compared with optima obtained by simulation of several sets of CUDA benchmarks. 1 |
| File Format | |
| Language | English |
| Publisher Date | 2011-01-01 |
| Access Restriction | Open |
| Subject Keyword | Scalar Behavior Cuda Kernel Adjacent Thread Uniform Control Flow Several Set Nvidia Cuda Program Compiler Pas Cuda Benchmark Consecutive Location Memory Access Multiple Data Common Computation Single Program Several Kind Simd Architecture Spmd Compiler Regular Pattern Ocelot Framework Ptx Intermediate Language Level Compiler Analysis Pas |
| Content Type | Text |
| Resource Type | Technical Report |
